Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 918 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3969. Min Act: -0.1700

Data Index: 561666 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3184. Min Act: -0.1700

Data Index: 351803 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3027. Min Act: -0.1700

Data Index: 543888 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3027. Min Act: -0.1700

Data Index: 111734 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2556. Min Act: -0.1700

Data Index: 1288213 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2556. Min Act: -0.1700

Data Index: 653954 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2084. Min Act: -0.1700

Data Index: 1175840 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2556. Min Act: -0.1700

Data Index: 249000 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2241. Min Act: -0.1700

Data Index: 463361 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2556. Min Act: -0.1700

Data Index: 355590 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2084. Min Act: -0.1700

Data Index: 628053 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1927. Min Act: -0.1700

Data Index: 734095 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2241. Min Act: -0.1700

Data Index: 899720 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1769. Min Act: -0.1700

Data Index: 77940 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2241. Min Act: -0.1700

Data Index: 177746 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1769. Min Act: -0.1700

Data Index: 275049 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1455. Min Act: -0.1700

Data Index: 825701 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1612. Min Act: -0.1700

Data Index: 518534 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1927. Min Act: -0.1700

Data Index: 573432 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.1927. Min Act: -0.1700

Data Index: 198063 (C4 (Web Text))

Max Activating Token Index: 545